A SMAP Supervised Classification of Landsat Images for Urban Sprawl Evaluation

Palma, Flavia Di; Amato, Federico; Nolè, Gabriele; Martellozzo, Federico; Murgante, Beniamino

doi:10.3390/ijgi5070109

Cited by 42 publications

(30 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Given this fact, obtaining the acceptable results for all classes is at the expense of accuracy degradation for certain cla sses. make them difficult to distinguish, while working with supervised classification method (Di Palma et al 2016). By introducing more features (such as textural or spectral features) into classification algorithm, we can expect that the algorithm would achieve the capability of better distinguishing the classes in some degree (Blaschke, Lang, and Hay 2008).…”

Section: Resultsmentioning

confidence: 99%

Object-based classification of hyperspectral data using Random Forest algorithm

Amini

Homayouni

Safari

et al. 2018

Geo-spatial Information Science

View full text Add to dashboard Cite

This paper presents a new framework for object-based classification of high-resolution hyperspectral data. This multi-step framework is based on multi-resolution segmentation (MRS) and Random Forest classifier (RFC) algorithms. The first step is to determine of weights of the input features while using the object-based approach with MRS to processing such images. Given the high number of input features, an automatic method is needed for estimation of this parameter. Moreover, we used the Variable Importance (VI), one of the outputs of the RFC, to determine the importance of each image band. Then, based on this parameter and other required parameters, the image is segmented into some homogenous regions. Finally, the RFC is carried out based on the characteristics of segments for converting them into meaningful objects. The proposed method, as well as, the conventional pixel-based RFC and Support Vector Machine (SVM) method was applied to three different hyperspectral data-sets with various spectral and spatial characteristics. These data were acquired by the HyMap, the Airborne Prism Experiment (APEX), and the Compact Airborne Spectrographic Imager (CASI) hyperspectral sensors. The experimental results show that the proposed method is more consistent for land cover mapping in various areas. The overall classification accuracy (OA), obtained by the proposed method was 95.48, 86.57, and 84.29% for the HyMap, the APEX, and the CASI datasets, respectively. Moreover, this method showed better efficiency in comparison to the spectralbased classifications because the OAs of the proposed method was 5.67 and 3.75% higher than the conventional RFC and SVM classifiers, respectively.

show abstract

Section: Resultsmentioning

confidence: 99%

Object-based classification of hyperspectral data using Random Forest algorithm

Amini

Homayouni

Safari

et al. 2018

Geo-spatial Information Science

View full text Add to dashboard Cite

show abstract

“…The term urban sprawl is related to the process of urban expansion with a dispersive and diffusive nature which, in the case of the mentioned cities, exceeds both boundaries of the historic centre and the crown surrounding the centre, completely saturating at the end of the 1980s [37,38]. The phenomenon also involves semi-central areas of Milan and Trieste, but it is more evident in the cities of Bari, Cagliari, Campobasso, Naples, and Genoa.…”

Section: Local Aspects and Peculiaritiesmentioning

confidence: 99%

The Dynamics of Urban Land Rent in Italian Regional Capital Cities

Manganelli

Murgante

2017

Land

Self Cite

View full text Add to dashboard Cite

This research tries to interpret the results of the empirical analysis of urban land value variations from 1977 to 2012 in the regional Italian capital cities based on the well-known theory of urban land rent. The historical series to be analyzed were obtained as the difference between the market value of a property and its cost of production. The paper shows, in quantitative terms, how differential and absolute rents will be translated into the dynamics of land values in relation to local specificities. The analysis of urban land rent evolution and the comparative study of the phenomenon compared to urban geography highlighted the difference among the various urban systems investigated and the criticalities generated by processes of transformation that have affected some Italian urban contexts. The difference is essentially explained by the different weight of macroeconomic variables, related to national and international contexts, and microeconomic variables, closely related to local demand and supply, in the process of rent formation.

show abstract

“…As largely recognised by scholars, the Landsat program strength lies in its continuity (e.g., Fichera et al, 2011Fichera et al, , 2012Di Palma et al, 2016). Moreover, the Landsat OLI and ETM+ sensors have proven to be a reliable source of data for land use (LU)/LC monitoring for the following characteristics: a relatively high spatial resolution (15÷30 m); a wide swath (the approximate scene size is 170 km North-South by 183 km East-West); a frequent repeat cycle of 16 days that can be potentially increased combining the data of the two sensors, thus reaching a theoretical repeat cycle of 8 days.…”

Section: Satellite Data Landsat 8 Archivesmentioning

confidence: 99%

Using Landsat 8 imagery in detecting cork oak (Quercus suber L.) woodlands: a case study in Calabria (Italy)

Modica

Merlino

Fazio

et al. 2016

J Agricult Engineer

View full text Add to dashboard Cite

In the Mediterranean basin, cork oak (Quercus suber L.) woodlands are characteristic and widespread forestry ecosystems. Though presenting significant economic potential as a renewable resource, they are not adequately valorised, in spite of a growing market demand for cork and cork-based products, which are appreciated, today, for their use in sustainable building. In this respect, cork meets the needs of the building industry in responding to the growing demand for quality products, which are eco-and energy-friendly and hygienically safe. Moreover, European cultural and biodiversity value has been attributed to cork oak woodlands and their most significant examples have been included in the Natura 2000 framework. So far, in some countries like Italy, the territorial distribution and characterisation of cork oak woodlands have not been adequately investigated. This study provides a method for mapping the actual presence of cork oak woodlands and for assessing their potential distribution. Special attention was given to the characterisation of cork oak spectral signature. To this end, Landsat 8 satellite images, digital photointerpretation and in situ surveys were implemented. The work carried out allows assessing the effectiveness of GIS and remote sensing techniques coupled with ancillary data and tools, and their applicability for the development of a comprehensive mapping and monitoring system of cork oak woodlands in Mediterranean ecosystems. Such techniques are vital to develop a detailed management strategy and to assist restoration activities and the economic assessment of semi-natural habitats. A case study, carried out in two different locations in Calabria (Italy), is provided.

show abstract

A SMAP Supervised Classification of Landsat Images for Urban Sprawl Evaluation

Cited by 42 publications

References 33 publications

Object-based classification of hyperspectral data using Random Forest algorithm

Object-based classification of hyperspectral data using Random Forest algorithm

The Dynamics of Urban Land Rent in Italian Regional Capital Cities

Using Landsat 8 imagery in detecting cork oak (Quercus suber L.) woodlands: a case study in Calabria (Italy)

Contact Info

Product

Resources

About